Efficacy of an artificial neural network-based approach to endoscopic ultrasound elastography in diagnosis of focal pancreatic masses

TY - JOUR

T1 - Efficacy of an artificial neural network-based approach to endoscopic ultrasound elastography in diagnosis of focal pancreatic masses

AU - Săftoiu, Adrian

AU - Vilmann, Peter

AU - Gorunescu, Florin

AU - Janssen, Jan

AU - Hocke, Michael

AU - Larsen, Michael

AU - Iglesias-Garcia, Julio

AU - Arcidiacono, Paolo

AU - Will, Uwe

AU - Giovannini, Marc

AU - Dietrich, Cristoph F

AU - Havre, Roald

AU - Gheorghe, Cristian

AU - McKay, Colin

AU - Gheonea, Dan Ionuţ

AU - Ciurea, Tudorel

AU - European EUS Elastography Multicentric Study Group

N1 - Copyright © 2012 AGA Institute. Published by Elsevier Inc. All rights reserved.

PY - 2012/1

Y1 - 2012/1

N2 - Background & Aims: By using strain assessment, real-time endoscopic ultrasound (EUS) elastography provides additional information about a lesion's characteristics in the pancreas. We assessed the accuracy of real-time EUS elastography in focal pancreatic lesions using computer-aided diagnosis by artificial neural network analysis. Methods: We performed a prospective, blinded, multicentric study at of 258 patients (774 recordings from EUS elastography) who were diagnosed with chronic pancreatitis (n = 47) or pancreatic adenocarcinoma (n = 211) from 13 tertiary academic medical centers in Europe (the European EUS Elastography Multicentric Study Group). We used postprocessing software analysis to compute individual frames of elastography movies recorded by retrieving hue histogram data from a dynamic sequence of EUS elastography into a numeric matrix. The data then were analyzed in an extended neural network analysis, to automatically differentiate benign from malignant patterns. Results: The neural computing approach had 91.14% training accuracy (95% confidence interval [CI], 89.87%-92.42%) and 84.27% testing accuracy (95% CI, 83.09%-85.44%). These results were obtained using the 10-fold cross-validation technique. The statistical analysis of the classification process showed a sensitivity of 87.59%, a specificity of 82.94%, a positive predictive value of 96.25%, and a negative predictive value of 57.22%. Moreover, the corresponding area under the receiver operating characteristic curve was 0.94 (95% CI, 0.91%-0.97%), which was significantly higher than the values obtained by simple mean hue histogram analysis, for which the area under the receiver operating characteristic was 0.85. Conclusions: Use of the artificial intelligence methodology via artificial neural networks supports the medical decision process, providing fast and accurate diagnoses.

AB - Background & Aims: By using strain assessment, real-time endoscopic ultrasound (EUS) elastography provides additional information about a lesion's characteristics in the pancreas. We assessed the accuracy of real-time EUS elastography in focal pancreatic lesions using computer-aided diagnosis by artificial neural network analysis. Methods: We performed a prospective, blinded, multicentric study at of 258 patients (774 recordings from EUS elastography) who were diagnosed with chronic pancreatitis (n = 47) or pancreatic adenocarcinoma (n = 211) from 13 tertiary academic medical centers in Europe (the European EUS Elastography Multicentric Study Group). We used postprocessing software analysis to compute individual frames of elastography movies recorded by retrieving hue histogram data from a dynamic sequence of EUS elastography into a numeric matrix. The data then were analyzed in an extended neural network analysis, to automatically differentiate benign from malignant patterns. Results: The neural computing approach had 91.14% training accuracy (95% confidence interval [CI], 89.87%-92.42%) and 84.27% testing accuracy (95% CI, 83.09%-85.44%). These results were obtained using the 10-fold cross-validation technique. The statistical analysis of the classification process showed a sensitivity of 87.59%, a specificity of 82.94%, a positive predictive value of 96.25%, and a negative predictive value of 57.22%. Moreover, the corresponding area under the receiver operating characteristic curve was 0.94 (95% CI, 0.91%-0.97%), which was significantly higher than the values obtained by simple mean hue histogram analysis, for which the area under the receiver operating characteristic was 0.85. Conclusions: Use of the artificial intelligence methodology via artificial neural networks supports the medical decision process, providing fast and accurate diagnoses.

U2 - 10.1016/j.cgh.2011.09.014

DO - 10.1016/j.cgh.2011.09.014

M3 - Journal article

SN - 1542-3565

VL - 10

SP - 84-90.e1

JO - Clinical Gastroenterology and Hepatology

JF - Clinical Gastroenterology and Hepatology

IS - 1

ER -